"TaScaaS: A Multi-Tenant Serverless Task Scheduler and Load Balancer as a Service" is a new scientific work published in cooperation with the AI-SPRINT project. The work hightights the benefits brought by TaScaaS, a service that can endure workload distribution across multiple infrastructures.


Paper Overview

  • Highlights the need for a service capable to handle workload distribution across multiple infrastructures to mitigate unpredictable performance fluctuations.
  • Presents TaScaaS, a highly scalable and completely serverless service deployed on AWS to distribute loosely coupled jobs among several computing infrastructures, and load balances them using a completely asynchronous approach to cope with the performance fluctuations with minimum impact in the execution time.
  • Shows how TaScaaS is not only capable of handling fluctuations efficiently, achieving a reduction in execution times up to 45% in the experiments, but can split the jobs to be computed to meet the user-defined execution time.





Cloud computing, heterogeneous computing, load balance, serverless


Download and read the paper